AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Collaborative Uncertainty in Multi-Agent Trajectory Forecasting

Bohan Tang, Yiqi Zhong, Ulrich Neumann, Gang Wang, Siheng Chen, Ya Zhang

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add collaborative uncertainty (full covariance) to individual uncertaintyGaussian noise model on synthetic data · Synthetic GaussianKL divergence: 6.68 -> 0.40Improved
add collaborative uncertainty to individual uncertaintyLaplace noise model on synthetic data · Synthetic LaplaceKL divergence: 12.6 -> 1.65Improved
add collaborative uncertaintyestimated covariance on synthetic Gaussian · Synthetic Gaussianl1 of covariance: 1.98 -> 1.01Improved
add collaborative uncertaintyestimated mean on synthetic Laplace · Synthetic Laplacel2 of mean: 0.42 -> 0.34Improved
add Laplace collaborative uncertainty loss to LaneGCNLaneGCN (our implementation) · Argoverse testADE: 1.76 -> 1.70Improved
add Laplace collaborative uncertainty loss to LaneGCNLaneGCN (our implementation) · Argoverse testFDE: 3.84 -> 3.74Improved
use Gaussian CU loss instead of Laplace CU lossLaneGCN with CU · Argoverse testADE: 1.73 vs 1.70Hurt
model full covariance instead of diagonal, with interaction module (ablation)LaneGCN Laplace · Argoverse valFDE: 3.16 -> 3.11Improved
model full covariance instead of diagonal, without interaction module (ablation)LaneGCN Laplace · Argoverse valADE: 1.67 -> 1.67No clear effect
model full covariance instead of diagonal, with interaction module (ablation)VectorNet Laplace · nuScenes valFDE: 9.79 -> 9.22Improved
model full covariance instead of diagonal, without interaction module (ablation)VectorNet Laplace · nuScenes valFDE: 10.25 -> 10.21Improved
model full covariance instead of diagonal, with interaction module (ablation)LaneGCN Gaussian · nuScenes valADE: 4.47 -> 4.39Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy